Edited, memorised or added to reading queue

on 16-Jun-2022 (Thu)

Do you want BuboFlash to help you learning these things? Click here to log in or create user.

#ML_in_Action #learning #machine #software-engineering
ML engineering applies a system around this staggering level of complexity. It uses a set of standards, tools, processes, and methodology that aims to minimize the chances of abandoned, misguided, or irrelevant work being done in an effort to solve a business problem or need. It, in essence, is the road map to creating ML-based systems that can be not only deployed to production, but also maintained and updated for years in the future, allowing businesses to reap the rewards in efficiency, profitability, and accuracy that ML, in general, has proven to provide (when done correctly).
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on

pdf

cannot see any pdfs




#causality #statistics
Causal edges assumption is asymmetric; β€œ 𝑋 is a cause of π‘Œ ” is not the same as saying β€œ π‘Œ is a cause of 𝑋
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on


Parent (intermediate) annotation

Open it

Original toplevel document (pdf)

cannot see any pdfs




Flashcard 7095738043660

Tags
#causality #statistics
Question

causal edges assumption, endows [...] paths with the unique role of carrying causation along them.

Additionally, causal edges assumption is asymmetric; β€œ 𝑋 is a cause of π‘Œ ” is not the same as saying β€œ π‘Œ is a cause of 𝑋 .”

Answer
directed

statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

Parent (intermediate) annotation

Open it
causal edges assumption, endows directed paths with the unique role of carrying causation along them. Additionally, causal edges assumption is asymmetric; β€œ 𝑋 is a cause of π‘Œ ” is not the same as saying β€œ π‘Œ is a cause of 𝑋 .”

Original toplevel document (pdf)

cannot see any pdfs







Flashcard 7095739878668

Tags
#causality #statistics
Question
[...] means that the treatment groups are exchangeable in the sense that if they were swapped, the new treatment group would observe the same outcomes as the old treatment group
Answer
Exchangeability

statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

Parent (intermediate) annotation

Open it
Exchangeability means that the treatment groups are exchangeable in the sense that if they were swapped, the new treatment group would observe the same outcomes as the old treatment group

Original toplevel document (pdf)

cannot see any pdfs







Flashcard 7095745383692

Tags
#Data #GAN #reading #synthetic
Question

The synthetic data that will populate the tables have to retain the properties of the original data. This is an additional challenge for the model since we have to preserve referential integrity, meaning that the foreign key β€” the column or group of columns that provide the link between two tables β€” in Table A has to match the corresponding items in Table B (if a relation is one-to-many). A possible solution to this problem is to synthesise data at [...] granularity levels:

1. Use unsupervised machine learning to cluster data at parent level (customer).

2. Synthesise this table, including the cluster identifier.

3. Randomly assign a synthesised customer to a real order sequence.

4. Finally synthesise the remaining variables (sequences at the child level) conditioned on the

previous data.

The problem with this solution is that it does not scale for very large databases.

Answer
multiple

statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

Parent (intermediate) annotation

Open it
hat provide the link between two tables β€” in Table A has to match the corresponding items in Table B (if a relation is one-to-many). A possible solution to this problem is to synthesise data at <span>multiple granularity levels: 1. Use unsupervised machine learning to cluster data at parent level (customer). 2. Synthesise this table, including the cluster identifier. 3. Randomly assign a syn

Original toplevel document (pdf)

cannot see any pdfs







Flashcard 7095747218700

Tags
#causality #statistics
Question
It turns out that much of the work for causal graphical models was done in the field of probabilistic graphical models. Probabilistic graphical models are statistical models while causal graphical models are [...] models.
Answer
causal

statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

Parent (intermediate) annotation

Open it
hat much of the work for causal graphical models was done in the field of probabilistic graphical models. Probabilistic graphical models are statistical models while causal graphical models are <span>causal models. <span>

Original toplevel document (pdf)

cannot see any pdfs







#causality #statistics
there is an important difference between association and causation: association is symmetric, whereas causation is asymmetric
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on


Parent (intermediate) annotation

Open it
paths with the unique role of carrying causation along them. Additionally, this assumption is asymmetric; β€œ 𝑋 is a cause of π‘Œ ” is not the same as saying β€œ π‘Œ is a cause of 𝑋 .” This means that <span>there is an important difference between association and causation: association is symmetric, whereas causation is asymmetric <span>

Original toplevel document (pdf)

cannot see any pdfs




Flashcard 7095750364428

Tags
#causality #statistics
Question

By β€œflow of association,” we mean whether any two nodes in a graph are associated or not associated. Another way of saying this is whether two nodes are (statistically) dependent or (statistically) independent.

Additionally, we will study whether two nodes are [...] independent or not.

Answer
conditionally

statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

Parent (intermediate) annotation

Open it
are associated or not associated. Another way of saying this is whether two nodes are (statistically) dependent or (statistically) independent. Additionally, we will study whether two nodes are <span>conditionally independent or not. <span>

Original toplevel document (pdf)

cannot see any pdfs







Flashcard 7095752723724

Tags
#causality #statistics
Question
The flow of [...] is symmetric
Answer
association

statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

Parent (intermediate) annotation

Open it
The flow of association is symmetric

Original toplevel document (pdf)

cannot see any pdfs







#Data #GAN #reading #synthetic
In generating synthesised data, normally we use the finest granularity. For instance, order_id would represent a store managing orders, or person_id could represent a population.
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on


Parent (intermediate) annotation

Open it
In generating synthesised data, normally we use the finest granularity. For instance, order_id would represent a store managing orders, or person_id could represent a population. However, when we have multiple tables linked by foreign keys, then different levels of granularity emerge and the concept of finest granularity becomes ambiguous

Original toplevel document (pdf)

cannot see any pdfs




Flashcard 7095756393740

Tags
#causality #statistics
Question
To get this guaranteed dependence between adjacent nodes, we will generally assume a slightly stronger assumption than the local Markov assumption: [...]
Answer
minimality

statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

Parent (intermediate) annotation

Open it
To get this guaranteed dependence between adjacent nodes, we will generally assume a slightly stronger assumption than the local Markov assumption: minimality

Original toplevel document (pdf)

cannot see any pdfs







Flashcard 7095758228748

Tags
#causality #statistics
Question

Flow of Causation

The flow of association is symmetric, whereas the flow of causation is not. Under the [...] assumption (Assumption 3.3), causation only flows in a single direction. Causation only flows along directed paths. Association flows along any path that does not contain an immorality

Answer
causal edges

statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

Parent (intermediate) annotation

Open it
Flow of Causation The flow of association is symmetric, whereas the flow of causation is not. Under the causal edges assumption (Assumption 3.3), causation only flows in a single direction. Causation only flows along directed paths. Association flows along any path that does not contain an immorality

Original toplevel document (pdf)

cannot see any pdfs







Flashcard 7095760063756

Tags
#causality #statistics
Question
The potential outcome that is observed is sometimes referred to as a factual. Note that there are no counterfactuals or factuals until the outcome is [...]. Before that, there are only potential outcomes
Answer
observed

statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

Parent (intermediate) annotation

Open it
The potential outcome that is observed is sometimes referred to as a factual. Note that there are no counterfactuals or factuals until the outcome is observed. Before that, there are only potential outcomes

Original toplevel document (pdf)

cannot see any pdfs







Flashcard 7095761898764

Tags
#causality #statistics
Question
In contrast, the non-strict causal edges assumption would allow for some parents to not be causes of their children. It would just assume that children are [...] of their parents. This allows us to draw graphs with extra edges to make fewer assumptions, just like we would in Bayesian networks, where more edges means fewer independence assumptions.
Answer
not causes

statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

Parent (intermediate) annotation

Open it
In contrast, the non-strict causal edges assumption would allow for some parents to not be causes of their children. It would just assume that children are not causes of their parents. This allows us to draw graphs with extra edges to make fewer assumptions, just like we would in Bayesian networks, where more edges means fewer independence assumption

Original toplevel document (pdf)

cannot see any pdfs







Flashcard 7095763995916

Tags
#causality #statistics
Question
there is no reason to expect that the groups are the same in all relevant variables other than the treatment. However, if we control for relevant variables by [...], then maybe the subgroups will be exchangeable. We will clarify what the β€œrelevant variables” are in Chapter 3,
Answer
conditioning

statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

Parent (intermediate) annotation

Open it
there is no reason to expect that the groups are the same in all relevant variables other than the treatment. However, if we control for relevant variables by conditioning, then maybe the subgroups will be exchangeable. We will clarify what the β€œrelevant variables” are in Chapter 3,

Original toplevel document (pdf)

cannot see any pdfs







Flashcard 7095766093068

Tags
#causality #statistics
Question
consistency encompasses the assumption that is sometimes referred to as β€œno [...] versions of treatment.”
Answer
multiple

statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

Parent (intermediate) annotation

Open it
consistency encompasses the assumption that is sometimes referred to as β€œno multiple versions of treatment.”

Original toplevel document (pdf)

cannot see any pdfs







Flashcard 7095767928076

Tags
#DAG #causal #edx
Question

Other (wrong definitions of confounder):

- change in estimate definition

- [...] definition

Answer
conventional

statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

Parent (intermediate) annotation

Open it
Other (wrong definitions of confounder): - change in estimate definition - conventional definition

Original toplevel document (pdf)

cannot see any pdfs







Flashcard 7095769500940

Tags
#DAG #causal #edx #has-images
[unknown IMAGE 7092564790540]
Question
Let's start by considering two extreme examples. In the first causal graph here you see that A and Y have no common causes. And therefore, any association between them will be causation. This is the setting that we expect to find in a [...].
Answer
randomized experiment

statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

Parent (intermediate) annotation

Open it
amples. In the first causal graph here you see that A and Y have no common causes. And therefore, any association between them will be causation. This is the setting that we expect to find in a <span>randomized experiment. <span>

Original toplevel document (pdf)

cannot see any pdfs







Flashcard 7095771598092

Tags
#causality #statistics
Question
Whenever, do(𝑑) appears after the conditioning bar, it means that everything in that expression is in the post-intervention world where the intervention do(𝑑) occurs. For example, 𝔼[π‘Œ | [...]] refers to the expected outcome in the subpopulation where 𝑍 = 𝑧 after the whole subpopulation has taken treatment 𝑑 .
Answer
do(𝑑), 𝑍 = 𝑧

statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

Parent (intermediate) annotation

Open it

Original toplevel document (pdf)

cannot see any pdfs







Flashcard 7095773433100

Tags
#DAG #causal #edx
Question
Systematic bias is an association between the treatment A and the outcome Y that does not arise from the [...] of A on Y.
Answer
causal effect

statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

Parent (intermediate) annotation

Open it
Systematic bias is an association between the treatment A and the outcome Y that does not arise from the causal effect of A on Y.

Original toplevel document (pdf)

cannot see any pdfs







Flashcard 7095775268108

Tags
#DAG #causal #edx #has-images
[unknown IMAGE 7092578422028]
Question
In the second graph here, you see that A and Y have a common cause, L. But there is no causal effect of A on Y. In this setting, all the association between A and Y is due to [...].
Answer
confounding

statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

Parent (intermediate) annotation

Open it
In the second graph here, you see that A and Y have a common cause, L. But there is no causal effect of A on Y. In this setting, all the association between A and Y is due to confounding.

Original toplevel document (pdf)

cannot see any pdfs







Flashcard 7095777365260

Tags
#causality #statistics
Question
Whenever, do(𝑑) appears after the conditioning bar, it means that everything in that expression is in the post-intervention world where the intervention [...] occurs.
Answer
do(𝑑)

statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

Parent (intermediate) annotation

Open it

Original toplevel document (pdf)

cannot see any pdfs